Inability to obtain trusted data and/or lack of data source alignment
Sequence Number
5
Industry
Seaports
Banner
How 5G enabled
Automated quality control employing machine learning with sensors collecting data and alerting during abnormal production for improvement purposes.
Data Flows
Title
Devices
Icon
Description
Collect all data required with or without sensors
Include broad spectrum of data sources to support the Digital Twin
Title
Connectivity
Icon
Description
Time series data transport
Camera images
Asset data (maintenance records) access
Title
Edge Compute
Icon
Description
Time critical activities
Camera – MV interpretation
Title
Cloud Compute & Storage
Icon
Description
All data collected from assets (both historical and real-time)
Enterprise-owned storage
Title
Applications & Services
Icon
Description
Non-time critical activities
Data Integration and Digital Twin type of support
E2E automated
Title
Inform Decision Makers
Icon
Description
Decisions made increasingly by AI processes based on AI models and decisions based on utilising Digital Twin
Title
Support Decision Making
Icon
Description
End of process
Application Logic
Description
Identify critical assets.
Collect event and/or timeseries data from these critical assets, potentially using sensors.
Collect camera images (fixed/drones /robotics/etc.).
Collect any other data sources that are relevant to Digital Twin and AI models, including operational and engineering data.
Edge + 5G to be used for all time critical events.
Description
All collected data from edge sensors will be stored long-term in Enterprise storage.
Development of the ML model is done through an iterative process. A quality ML model (fully data-driven) will require multiple steps to detect anomalies/potential failures.
Models will be stored and maintained by AI applications.
SME involvement working with data scientist is required to develop the model.
Description
Data is accessible via Digital Twin: Integration and Visualisation layer.
Digital Twin is accessible to all Port workers.
The process from data collection to execution of models is fully automated.
Only alerts operations when anomalies are detected in data behaviour. Over time as ML model strengthens, AI decisions will increase without the need for operator involvement
Using XR to view 3D models
Expected benefits
Proactive detection of abnormalities and preventative actions
Improve productivity from reduced unplanned downtime
Reduce maintenance cost due to early spotting of issues
Shorter turnaround times due to more targeted maintenance
Key value created
Better access to data leading to faster and improved decision making